Since their inception in the 1940s, deep learning systems have experienced a resurgence through the advent of Big Data, stronger computational systems and more intuitive software. Neural networks allow vast amounts of data to be processed in relatively short periods of time in comparison to both traditional methods of empirical testing and more advanced methods such as Density Functional Theory, resulting in shorter and more efficient development cycles. Their self-iterative nature allows for accurate analysis of data which leads to lower error rates; with a particular rate of less than 4% in fatigue and metal corrosion detection.
This lecture explores the fundamental principles of deep learning, its challenges, advantages, how it is currently being utilised in the materials industry and how it can further be used as one of science’s most powerful tools.

Using Complementary Characterisation Techniques to Understand Radiation Damage in Nuclear Reactor Pressure Vessels by Alex Dickinson-Lomas.

Extending the lifetime of nuclear reactors to improve sustainability is essential for the global future of energy generation. The critical component, the reactor pressure vessel (RPV), is subjected to extreme radiation conditions for over 50 years and must maintain structural integrity to ensure safe and secure reactor operation. Understanding the mechanisms and changes in microstructure and mechanical properties of RPV steels will enable more accurate prediction of lifelong performance. Combining a wide range of complementary characterisation techniques holds the key to understanding how these materials change in harsh environments and how we can create better predictive models for their behaviour. This talk will briefly explain how combining techniques such as mechanical testing, transmission electron microscopy, atom probe tomography and small angle neutron scattering, is not only useful but necessary to underpin predictions and understand material behaviour.

Will COVID-19 force us to rethink our materials for high touch surfaces? By Ellen Davidson.

Lifts propose a particular challenge when trying to reduce the spread of COVID-19, as social distancing cannot be easily achieved and lifts have many high touch surfaces.
At the beginning of the pandemic, I analysed how to control the spread of COVID-19 in lifts socially. I am now researching how material selection can be used to prevent cross contamination through high touch surfaces.
Introducing antimicrobial materials to common touch surfaces can reduce the spread of bacteria, virus and fungi. Currently, there are limited applications of antimicrobial surfaces but, in recent months, enquiries for surfaces such as lift buttons have risen rapidly.
Historically, antimicrobial materials, such as copper, have been used to reduce the spread of bacteria and viruses however, with the development of other metal alloys, the benefit of copper has been forgotten.

To register for this free to attend event, please email info@bmeta.co.uk

Subscribe to our email newsletters.

Details of any forthcoming talks/events will be listed on the programme page.

Interested people are warmly invited to come along to these events. Email us for more info if you wish to attend or become a member.

If you are a student and interested in joining the IOM3 with all of its attendant benefits, including a route to professional membership grades and free access to a wide range of refereed journals please email us, we can help and advise.

The BMetA is an affiliated local society of the IOM3

Click here to subscribe to our email newsletters.